Skip to content
Tagged articles

few-step generation

5 articles · Page 1 of 1
Machine Heart
Machine Heart
Oct 11, 2026 · Artificial Intelligence

Tsinghua's MGFlow & Elastic Forcing: Distributional Training for One-Step Images & Streaming Video

Tsinghua researchers introduce MGFlow and Elastic Forcing, two distributional training methods that achieve state-of-the-art one-step image generation and enable efficient 14B-parameter streaming video model post-training on just 8 GPUs, using sample distribution matching instead of per-sample supervision.

Elastic ForcingMGFlowPost-Training
0 likes · 20 min read
Tsinghua's MGFlow & Elastic Forcing: Distributional Training for One-Step Images & Streaming Video
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 12, 2026 · Artificial Intelligence

Achieving 4‑Step Diffusion Generation by Replacing MSE with Perceptual Loss in Five Lines of Code

By swapping the traditional MSE loss for a perceptual loss in Flow Matching training, the authors enable high‑quality diffusion generation in only 4–8 inference steps—down from 35–50—without teacher models, distribution or trajectory distillation, and they substantiate the claim with extensive experiments and a new distribution‑distance metric.

Computer VisionDistribution DistanceFlow Matching
0 likes · 7 min read
Achieving 4‑Step Diffusion Generation by Replacing MSE with Perceptual Loss in Five Lines of Code
AIWalker
AIWalker
May 20, 2026 · Artificial Intelligence

AnyFlow: Generate High‑Quality Video in 4 Steps and Keep Improving with More Sampling

AnyFlow introduces a flow‑map distillation framework that enables video diffusion models to produce high‑quality results in just four sampling steps while still gaining quality as the number of steps increases, supporting both causal and bidirectional architectures and scaling up to 14 B parameters.

On-Policy Distillationbidirectional videocausal video
0 likes · 14 min read
AnyFlow: Generate High‑Quality Video in 4 Steps and Keep Improving with More Sampling
SuanNi
SuanNi
Apr 12, 2026 · Artificial Intelligence

How TDM‑R1 Achieves 4‑Step Image Generation that Beats 80‑Step Models

Researchers from HKUST, CUHK and XiaoHongShu introduced TDM‑R1, a reinforcement‑learning‑based method that enables 4‑step diffusion image generation to surpass 80‑step models in speed, fidelity, and complex instruction adherence, as demonstrated on the GenEval benchmark and multiple quality metrics.

AI image synthesisbenchmarkingdiffusion models
0 likes · 9 min read
How TDM‑R1 Achieves 4‑Step Image Generation that Beats 80‑Step Models
AIWalker
AIWalker
Apr 7, 2025 · Artificial Intelligence

TurboFill: High‑Quality Image Inpainting in Just 4 Steps

TurboFill introduces a fast image‑inpainting model that trains a repair adapter on a few‑step text‑to‑image diffusion backbone, achieving state‑of‑the‑art results with only four diffusion steps while dramatically reducing computational cost.

Computer VisionTurboFilldiffusion models
0 likes · 17 min read
TurboFill: High‑Quality Image Inpainting in Just 4 Steps